AI and Heart Imaging Team Up to Find Better Heart Disease Treatments

Researchers have developed a groundbreaking method that combines artificial intelligence with heart imaging to identify existing drugs that could be repurposed for better cardiovascular treatment. The approach, called CardioKG, integrates detailed heart structure and function from medical images directly into biological knowledge networks, potentially accelerating the discovery of new heart disease therapies.

How Does This AI Heart Imaging System Work?

The CardioKG system works by adding cardiac imaging data to knowledge graphs—digital networks that connect information about genes, diseases, treatments, and molecular pathways. While traditional knowledge graphs have relied on population-level data, this new approach captures individual patient variations in how disease actually affects the heart itself.

To build their model, researchers at the Computational Cardiac Imaging Group at the MRC Laboratory of Medical Sciences in London gathered cardiac imaging data from 4,280 patients with atrial fibrillation, heart attack, or heart failure from the UK Biobank, along with 5,304 healthy participants. From these scans, they generated more than 200,000 image-based traits defining heart structure and function, then integrated this information with data from 18 biological databases.

What Promising Drug Discoveries Did the AI Make?

The CardioKG system identified several exciting drug repurposing opportunities that could transform heart disease treatment. The AI predictions revealed potential new uses for existing medications:

• Methotrexate for Heart Failure: This rheumatoid arthritis drug showed promise as a candidate treatment for heart failure patients
• Gliptins for Atrial Fibrillation: These diabetes medications emerged as potential treatments for irregular heart rhythms
• Caffeine's Protective Effect: The model suggested a protective association between caffeine and atrial fibrillation in patients with irregular and fast heart rhythms

"What's exciting is there are other recent studies in the field which support our preliminary findings," said senior author Declan O'Regan, PhD, a principal investigator at MRC. "[This] highlights the huge potential of knowledge graphs in uncovering existing drugs that might be repurposed as new treatments."

Why Could This Change Heart Disease Care?

This breakthrough addresses a critical bottleneck in cardiovascular medicine. While genome-wide association studies have identified many disease-linked genetic variants, they haven't been able to pinpoint specific actionable treatment targets. The addition of imaging data creates "endophenotypes" that are much closer to actual disease mechanisms than many observable traits.

The implications for clinical care point to earlier and more precise identification of therapeutic targets on a patient-by-patient basis. By quickly identifying high-priority genes and candidate drugs, imaging-enhanced knowledge graphs could guide pharmaceutical development and enable more targeted clinical trials. Data from this study showed that predicted drug repurposing for heart failure could improve patient survival.

The research team is now planning to extend CardioKG into a dynamic, patient-centered framework that captures real disease trajectories. "Building on this work, we will extend the knowledge graph into a dynamic, patient-centered framework that captures real disease trajectories," said first author Khaled Rjoob, PhD, a postdoctoral researcher at Imperial College London. They also plan to include more diverse imaging datasets and apply the same approach to brain and body fat imaging.